Pub Date : 2025-02-24DOI: 10.1016/j.compeleceng.2025.110188
Zhongbao Lin, Desheng Rong
Accurately capturing long-term and short-term dependencies and cyclical relationships are core elements in determining photovoltaic prediction accuracy. In this paper, a novel method named PQTCN-MPC, which integrates a Parallel Quadratic Temporal Convolutional Network (PQTCN) with a Multi-Position Coding (MPC) Transformer, is proposed. First, PQTCN effectively extracts long and short-term depth dependencies of time series. Subsequently, the extracted features are encoded using MPC and Embedding, and the encoded features are concatenated. Finally, the output is obtained through an encoder and decoder structure. This study utilizes publicly available data from the Yulala solar system with three different resolutions. Ablation experiments validate that PQTCN-MPC enhances R2 by 3.69 %, NRMSE by 21.11 %, and MAE by 48.35 % at a minimum. Experimental results indicated that PQTCN-MPC enhanced R2 by 4.73 % under various seasonal conditions, while keeping NRMSE below 5 %, which underscores its high prediction accuracy and wide applicability.
{"title":"Integrating PQTCN-MPC with innovation: A new strategy for accurate PV power prediction","authors":"Zhongbao Lin, Desheng Rong","doi":"10.1016/j.compeleceng.2025.110188","DOIUrl":"10.1016/j.compeleceng.2025.110188","url":null,"abstract":"<div><div>Accurately capturing long-term and short-term dependencies and cyclical relationships are core elements in determining photovoltaic prediction accuracy. In this paper, a novel method named PQTCN-MPC, which integrates a Parallel Quadratic Temporal Convolutional Network (PQTCN) with a Multi-Position Coding (MPC) Transformer, is proposed. First, PQTCN effectively extracts long and short-term depth dependencies of time series. Subsequently, the extracted features are encoded using MPC and Embedding, and the encoded features are concatenated. Finally, the output is obtained through an encoder and decoder structure. This study utilizes publicly available data from the Yulala solar system with three different resolutions. Ablation experiments validate that PQTCN-MPC enhances <em>R</em><sup>2</sup> by 3.69 %, <em>NRMSE</em> by 21.11 %, and <em>MAE</em> by 48.35 % at a minimum. Experimental results indicated that PQTCN-MPC enhanced <em>R</em><sup>2</sup> by 4.73 % under various seasonal conditions, while keeping <em>NRMSE</em> below 5 %, which underscores its high prediction accuracy and wide applicability.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110188"},"PeriodicalIF":4.0,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Accurate and reliable forecasting of solar irradiance is necessary for an efficient grid performance with large scale penetration of photovoltaic (PV) generation. Thus, with an aim to improve solar irradiance forecasting accuracy, a new decomposition based hybrid model known as Stacked Long-Short-Term-Memory (LSTM) recurrent neural network is proposed in this paper. Further the dense layer of the stacked LSTM architecture is replaced by a novel Recurrent Ensemble Deep Random Vector Functional Link Network (REDRVFLN) to improve generalisation, speed up computation, and prediction accuracy. The raw irradiance data is pre-processed using Isolation Forest (IF) algorithm to remove the presence of outliers from the data and the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) algorithm decomposes the pre-processed data into Intrinsic Mode Functions (IMFs) with zero reconstruction error and better separation of spectral components. The recurrent stacked LSTM neural network effectively captures the temporal features and long term dependencies of decomposed solar irradiance time series data. On the other hand REDRVFLN model comprising several stacked layers of locally recurrent neurons with fixed random weights and biases effectively handles processed temporal features from the LSTM module with optimal generalisation and improved stability. Further the ensemble of the outputs from each layer produces the final forecast with better accuracy in comparison to many widely used deep neural network and other benchmark models. The performance of the proposed stacked LSTM integrated REDRVFLN model has been validated using solar irradiance data samples both hourly and with seasonal variations producing superior accuracy.
{"title":"Solar Irradiance Forecasting using Hybrid Long-Short-Term-Memory based Recurrent Ensemble Deep Random Vector Functional Link Network","authors":"Smruti Rekha Pattnaik , Ranjeeta Bisoi , P.K. Dash","doi":"10.1016/j.compeleceng.2025.110174","DOIUrl":"10.1016/j.compeleceng.2025.110174","url":null,"abstract":"<div><div>Accurate and reliable forecasting of solar irradiance is necessary for an efficient grid performance with large scale penetration of photovoltaic (PV) generation. Thus, with an aim to improve solar irradiance forecasting accuracy, a new decomposition based hybrid model known as Stacked Long-Short-Term-Memory (LSTM) recurrent neural network is proposed in this paper. Further the dense layer of the stacked LSTM architecture is replaced by a novel Recurrent Ensemble Deep Random Vector Functional Link Network (REDRVFLN) to improve generalisation, speed up computation, and prediction accuracy. The raw irradiance data is pre-processed using Isolation Forest (IF) algorithm to remove the presence of outliers from the data and the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) algorithm decomposes the pre-processed data into Intrinsic Mode Functions (IMFs) with zero reconstruction error and better separation of spectral components. The recurrent stacked LSTM neural network effectively captures the temporal features and long term dependencies of decomposed solar irradiance time series data. On the other hand REDRVFLN model comprising several stacked layers of locally recurrent neurons with fixed random weights and biases effectively handles processed temporal features from the LSTM module with optimal generalisation and improved stability. Further the ensemble of the outputs from each layer produces the final forecast with better accuracy in comparison to many widely used deep neural network and other benchmark models. The performance of the proposed stacked LSTM integrated REDRVFLN model has been validated using solar irradiance data samples both hourly and with seasonal variations producing superior accuracy.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110174"},"PeriodicalIF":4.0,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Plant Electronic Medical Records (PEMRs), containing crop disease and environmental data, provide a novel approach for disease diagnosis. However, training a federated learning (FL) model with PEMRs distributed across multiple devices poses challenges, such as opaque aggregation processes, risks of Byzantine faults, and high communication overhead. In this paper, we develop a blockchain-based multi-region federated learning (BMRFL) framework for crop disease diagnosis, incorporating the consortium blockchain technology to ensure that the process is both verifiable and resistant to attacks. We introduce the Musig2 Signature-based Practical Byzantine Fault Tolerance (M2SPBFT) protocol, which leverages the Musig2 algorithm to improve efficiency by reducing communication overhead and streamlining the verification process. Furthermore, we develop a aggregation strategy that boosts the global model's accuracy in diagnosing crop diseases. We constructed PEMR datasets with 23,702 samples from Beijing Plant Clinics to validate the BMRFL. Extensive experiments revealed that the BMRFL framework improved Byzantine fault resistance, lowered consensus communication overhead, and enhanced diagnostic accuracy across districts, achieving a 10.44 % accuracy increase in Haidian over previous methods. These results demonstrate the effectiveness and security of BMRFL in crop disease diagnosis, suggesting its potential for related diagnostic applications.
{"title":"An improved blockchain-based multi-region Federated Learning framework for crop disease diagnosis","authors":"Yuanze Qin , Chang Xu , Qin Zhou , Lingxian Zhang , Yiding Zhang","doi":"10.1016/j.compeleceng.2025.110181","DOIUrl":"10.1016/j.compeleceng.2025.110181","url":null,"abstract":"<div><div>Plant Electronic Medical Records (PEMRs), containing crop disease and environmental data, provide a novel approach for disease diagnosis. However, training a federated learning (FL) model with PEMRs distributed across multiple devices poses challenges, such as opaque aggregation processes, risks of Byzantine faults, and high communication overhead. In this paper, we develop a blockchain-based multi-region federated learning (BMRFL) framework for crop disease diagnosis, incorporating the consortium blockchain technology to ensure that the process is both verifiable and resistant to attacks. We introduce the Musig2 Signature-based Practical Byzantine Fault Tolerance (M2SPBFT) protocol, which leverages the Musig2 algorithm to improve efficiency by reducing communication overhead and streamlining the verification process. Furthermore, we develop a aggregation strategy that boosts the global model's accuracy in diagnosing crop diseases. We constructed PEMR datasets with 23,702 samples from Beijing Plant Clinics to validate the BMRFL. Extensive experiments revealed that the BMRFL framework improved Byzantine fault resistance, lowered consensus communication overhead, and enhanced diagnostic accuracy across districts, achieving a 10.44 % accuracy increase in Haidian over previous methods. These results demonstrate the effectiveness and security of BMRFL in crop disease diagnosis, suggesting its potential for related diagnostic applications.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110181"},"PeriodicalIF":4.0,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-22DOI: 10.1016/j.compeleceng.2025.110179
Adil Adam , Firat Kacar , Nikos Mastorakis
This study focuses on the design and implementation of an innovative eleven-level cascaded H-Bridge motor drive (11L-CHBMD) controlled by a three-phase step-sine pulse width modulation (SSPWM) technique. A novel mathematical model was developed by converting control equations into matrix format, facilitating precise simulation and practical realization of the system. MATLAB Simulink was employed for the simulation, while the STM32F429ZGT6 microcontroller and power MOSFETs were used for hardware implementation. The proposed system ensures a regulated high-voltage, variable-current output and achieves harmonic distortion levels below 5 %, in compliance with IEEE-519 standards. Experimental results showed the motor driver 11L-CHBMD's high capability to drive three-phase induction motors efficiently, offering superior performance compared to conventional topologies. The SSPWM method reduced total harmonic distortion (THD) while maintaining system stability under ohmic, inductive, and unbalanced load conditions. Fuzzy and PID controllers enabled precise torque, speed, and current regulation while stabilising faster. The 11L-CHBMD proposed circuit, developed using commonly available components, achieves a cost reduction of approximately 90 % compared to market-available designs, making it suitable for industrial, renewable energy and different applications. Its modular design supports scalability and offers potential for driving motors in hazardous environments or remote areas using solar energy. With its adaptability and efficiency, the proposed 11L-CHBMD stands as a compelling alternative to traditional power inverters.
{"title":"Enhancement design of eleven-level cascaded h-bridge motor driver application","authors":"Adil Adam , Firat Kacar , Nikos Mastorakis","doi":"10.1016/j.compeleceng.2025.110179","DOIUrl":"10.1016/j.compeleceng.2025.110179","url":null,"abstract":"<div><div>This study focuses on the design and implementation of an innovative eleven-level cascaded H-Bridge motor drive (11L-CHBMD) controlled by a three-phase step-sine pulse width modulation (SSPWM) technique. A novel mathematical model was developed by converting control equations into matrix format, facilitating precise simulation and practical realization of the system. MATLAB Simulink was employed for the simulation, while the STM32F429ZGT6 microcontroller and power MOSFETs were used for hardware implementation. The proposed system ensures a regulated high-voltage, variable-current output and achieves harmonic distortion levels below 5 %, in compliance with IEEE-519 standards. Experimental results showed the motor driver 11L-CHBMD's high capability to drive three-phase induction motors efficiently, offering superior performance compared to conventional topologies. The SSPWM method reduced total harmonic distortion (THD) while maintaining system stability under ohmic, inductive, and unbalanced load conditions. Fuzzy and PID controllers enabled precise torque, speed, and current regulation while stabilising faster. The 11L-CHBMD proposed circuit, developed using commonly available components, achieves a cost reduction of approximately 90 % compared to market-available designs, making it suitable for industrial, renewable energy and different applications. Its modular design supports scalability and offers potential for driving motors in hazardous environments or remote areas using solar energy. With its adaptability and efficiency, the proposed 11L-CHBMD stands as a compelling alternative to traditional power inverters.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110179"},"PeriodicalIF":4.0,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-22DOI: 10.1016/j.compeleceng.2025.110189
Eamin Chaudary, Sheeraz Ahmad Khan, Wajid Mumtaz
Emotion recognition is a key aspect of human–robot interaction (HRI), which requires social intelligence to perceive and react to human affective states. This paper introduces EEG-CNN-Souping, a novel approach that applies the “Model Soups” technique to a self-designed EEG-CNN model for classifying electroencephalogram (EEG) signals into emotions. EEG-CNN-Souping improves the model performance and efficiency by averaging the weights of multiple EEG-CNN models trained on different sizes of scalograms, which are acquired by applying continuous wavelet transform (CWT) and normalization to the EEG signals. The scalograms capture the time-varying patterns of the EEG signals effectively. The approach also uses data augmentation and gradient class activation map (Grad-Cam) visualization for robustness and interpretability respectively. The model is evaluated on a common dataset that is the SEED dataset and achieves a 99.31% accuracy, surpassing other state-of-the-art deep learning (DL) models in terms of accuracy, computational cost, and time efficiency. The prediction time for EEG-CNN-Souping is only 6 ms. The explainable artificial intelligence (XAI) method Grad-CAM is utilized for interpretation of predictions. EEG-CNN-Souping is computationally inexpensive and time-efficient.
{"title":"EEG-CNN-Souping: Interpretable emotion recognition from EEG signals using EEG-CNN-souping model and explainable AI","authors":"Eamin Chaudary, Sheeraz Ahmad Khan, Wajid Mumtaz","doi":"10.1016/j.compeleceng.2025.110189","DOIUrl":"10.1016/j.compeleceng.2025.110189","url":null,"abstract":"<div><div>Emotion recognition is a key aspect of human–robot interaction (HRI), which requires social intelligence to perceive and react to human affective states. This paper introduces EEG-CNN-Souping, a novel approach that applies the “Model Soups” technique to a self-designed EEG-CNN model for classifying electroencephalogram (EEG) signals into emotions. EEG-CNN-Souping improves the model performance and efficiency by averaging the weights of multiple EEG-CNN models trained on different sizes of scalograms, which are acquired by applying continuous wavelet transform (CWT) and normalization to the EEG signals. The scalograms capture the time-varying patterns of the EEG signals effectively. The approach also uses data augmentation and gradient class activation map (Grad-Cam) visualization for robustness and interpretability respectively. The model is evaluated on a common dataset that is the SEED dataset and achieves a 99.31% accuracy, surpassing other state-of-the-art deep learning (DL) models in terms of accuracy, computational cost, and time efficiency. The prediction time for EEG-CNN-Souping is only 6 ms. The explainable artificial intelligence (XAI) method Grad-CAM is utilized for interpretation of predictions. EEG-CNN-Souping is computationally inexpensive and time-efficient.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110189"},"PeriodicalIF":4.0,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To pave the way to a super-smart society, artificial intelligence (AI) methods are being developed to discover and analyze necessary information instantly from cyberspace and utilize it in physical space. However, privacy protection is necessary for AI to process big data in cyberspace. From the viewpoint of developing safe and secure machine learning methods, research on (1) homomorphic cryptography, (2) differential privacy, (3) secure multiparty computation, and (4) federated learning is underway. The goal of these studies is to develop useful learning methods while maintaining data privacy.
We propose a method to address the trade-off between security and usability in machine learning. This method balances usability and data confidentiality by using decomposed data to achieve secure distributed processing. However, such methods using distributed processing increase computational and communication overhead as the number of servers increases. To address this problem, we propose a method to control the computational complexity as the number of servers increases. On the basis of these studies, this study first systematically addresses the construction of secure distributed processing methods with decomposed data. A comprehensive approach is essential to advance the field and allow these methods to be effectively applied to different domains. On the basis of these methods, we propose back-propagation and neural gas learning methods with reduced computational and communication requirements. We then apply the proposed methods to numerical simulations of class classification and clustering problems and show that accuracy comparable to that of conventional models can be achieved with computational and communication complexity for distributed models with servers.
{"title":"Toward the development of learning methods with distributed processing using securely divided data","authors":"Hirofumi Miyajima , Noritaka Shigei , Hiromi Miyajima , Norio Shiratori","doi":"10.1016/j.compeleceng.2025.110160","DOIUrl":"10.1016/j.compeleceng.2025.110160","url":null,"abstract":"<div><div>To pave the way to a super-smart society, artificial intelligence (AI) methods are being developed to discover and analyze necessary information instantly from cyberspace and utilize it in physical space. However, privacy protection is necessary for AI to process big data in cyberspace. From the viewpoint of developing safe and secure machine learning methods, research on (1) homomorphic cryptography, (2) differential privacy, (3) secure multiparty computation, and (4) federated learning is underway. The goal of these studies is to develop useful learning methods while maintaining data privacy.</div><div>We propose a method to address the trade-off between security and usability in machine learning. This method balances usability and data confidentiality by using decomposed data to achieve secure distributed processing. However, such methods using distributed processing increase computational and communication overhead as the number of servers increases. To address this problem, we propose a method to control the computational complexity as the number of servers increases. On the basis of these studies, this study first systematically addresses the construction of secure distributed processing methods with decomposed data. A comprehensive approach is essential to advance the field and allow these methods to be effectively applied to different domains. On the basis of these methods, we propose back-propagation and neural gas learning methods with reduced computational and communication requirements. We then apply the proposed methods to numerical simulations of class classification and clustering problems and show that accuracy comparable to that of conventional models can be achieved with <span><math><mrow><mn>1</mn><mo>/</mo><mi>Q</mi></mrow></math></span> computational and communication complexity for distributed models with <span><math><mi>Q</mi></math></span> servers.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110160"},"PeriodicalIF":4.0,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-21DOI: 10.1016/j.compeleceng.2025.110178
Yuge Niu , Chao Zhang , Arun Kumar Sangaiah , Kexin Liu , Fanghui Lu , Mohammed J.F. Alenazi , Salman A. AlQahtani
In urban traffic management, bike-sharing systems are crucial for green transportation. However, due to the uneven distribution of shared bikes and randomization of user behavior, the urban dockless bicycle sharing system (UDBSS) faces issues of randomization. Since rebalancing in UDBSS involves the opinion and preference of multiple stakeholders, it can be modeled as a group consensus problem. Nevertheless, mutual influence among users, changing preferences, and psychological inconsistencies, along with the absence of personalized strategies in traditional methods, adversely affect demand decisions for UDBSS. To address this issue, this paper innovatively combines random vector functional link (RVFL) networks, quantum theory (QT), and prospect–regret theory (P–RT), to construct a personalized two-stage group consensus framework. First, with the support of three-way decisions, an improved K-means++ algorithm based on Euclidean distances and Hausdorff distances is used for clustering, which reduces the uncertainty in the UDBSS problem. Additionally, to address the randomization issue, RVFL is used to calculate intragroup user weights, and the chimp optimization algorithm (CHOA) is applied for the hyperparameter optimization. Furthermore, considering users’ psychological behavior, a two-stage consensus reaching process (CRP) is designed, and a personalized adjustment mechanism based on QT, P–RT, and hesitation degrees is proposed. Finally, the proposed model is applied to a shared bicycle deployment scenario, with experimental analysis using data from the Citi Bike system and survey data to verify its effectiveness and feasibility.
{"title":"Intelligent traffic management via personalized group consensus based on chimp optimization-guided random vector functional link and quantum theory: A perspective of randomization","authors":"Yuge Niu , Chao Zhang , Arun Kumar Sangaiah , Kexin Liu , Fanghui Lu , Mohammed J.F. Alenazi , Salman A. AlQahtani","doi":"10.1016/j.compeleceng.2025.110178","DOIUrl":"10.1016/j.compeleceng.2025.110178","url":null,"abstract":"<div><div>In urban traffic management, bike-sharing systems are crucial for green transportation. However, due to the uneven distribution of shared bikes and randomization of user behavior, the urban dockless bicycle sharing system (UDBSS) faces issues of randomization. Since rebalancing in UDBSS involves the opinion and preference of multiple stakeholders, it can be modeled as a group consensus problem. Nevertheless, mutual influence among users, changing preferences, and psychological inconsistencies, along with the absence of personalized strategies in traditional methods, adversely affect demand decisions for UDBSS. To address this issue, this paper innovatively combines random vector functional link (RVFL) networks, quantum theory (QT), and prospect–regret theory (P–RT), to construct a personalized two-stage group consensus framework. First, with the support of three-way decisions, an improved K-means++ algorithm based on Euclidean distances and Hausdorff distances is used for clustering, which reduces the uncertainty in the UDBSS problem. Additionally, to address the randomization issue, RVFL is used to calculate intragroup user weights, and the chimp optimization algorithm (CHOA) is applied for the hyperparameter optimization. Furthermore, considering users’ psychological behavior, a two-stage consensus reaching process (CRP) is designed, and a personalized adjustment mechanism based on QT, P–RT, and hesitation degrees is proposed. Finally, the proposed model is applied to a shared bicycle deployment scenario, with experimental analysis using data from the Citi Bike system and survey data to verify its effectiveness and feasibility.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110178"},"PeriodicalIF":4.0,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-21DOI: 10.1016/j.compeleceng.2025.110149
Pitchala Vijaya Kumar, C. Shilaja
Scheduling power generators to decrease costs and meet system restrictions is known as economic load dispatch, or ELD, in power systems. While earlier research works have demonstrated strategies to lower production costs and carbon dioxide emissions, an ideal distribution of costs and pollutants must be taken into account, resulting in Combined Emission Dispatch (CED). The main contribution of this study is the formulation of a new hybrid meta-heuristic model for solving the ELD and CED problem, called the Raccoon Yin Yang Pair Optimization (RYi-YaP) model. To minimize the fuel costs in order to maximize the financial advantages of power systems. Power balance and generator power limit are two restrictions that are focused on in this work in order to efficiently optimize the ELD process. In addition, a thorough analysis is conducted to investigate the performance of the proposed approach under various load conditions. The generators must meet the load requirement with the least amount of gearbox loss in order to guarantee safe operation. This study also considers some of the most popular and widely used optimization procedures for a comprehensive performance comparison and evaluation. The performance of the proposed approach is found to be quite satisfactory when compared to the previously reviewed approaches.
{"title":"A swank raccoon yin yang pair optimization (RYi-YaP) model for solving economic load dispatch (ELD) and combined emission dispatch (CED) problems","authors":"Pitchala Vijaya Kumar, C. Shilaja","doi":"10.1016/j.compeleceng.2025.110149","DOIUrl":"10.1016/j.compeleceng.2025.110149","url":null,"abstract":"<div><div>Scheduling power generators to decrease costs and meet system restrictions is known as economic load dispatch, or ELD, in power systems. While earlier research works have demonstrated strategies to lower production costs and carbon dioxide emissions, an ideal distribution of costs and pollutants must be taken into account, resulting in Combined Emission Dispatch (CED). The main contribution of this study is the formulation of a new hybrid meta-heuristic model for solving the ELD and CED problem, called the Raccoon Yin Yang Pair Optimization (RYi-YaP) model. To minimize the fuel costs in order to maximize the financial advantages of power systems. Power balance and generator power limit are two restrictions that are focused on in this work in order to efficiently optimize the ELD process. In addition, a thorough analysis is conducted to investigate the performance of the proposed approach under various load conditions. The generators must meet the load requirement with the least amount of gearbox loss in order to guarantee safe operation. This study also considers some of the most popular and widely used optimization procedures for a comprehensive performance comparison and evaluation. The performance of the proposed approach is found to be quite satisfactory when compared to the previously reviewed approaches.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110149"},"PeriodicalIF":4.0,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143455017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-21DOI: 10.1016/j.compeleceng.2025.110161
Himanshu Nandanwar, Rahul Katarya
Cyber-physical systems (CPS) security is critical, particularly with the advent of Industry 5.0, which seeks to revolutionize industrial ecosystems through enhanced automation, connectivity, and human-machine collaboration. While this shift promises increased efficiency and productivity, it exposes systems to advanced cyber threats. This paper introduces Cyber-Sentinet, a Deep Learning-based Intrusion Detection System (IDS) designed explicitly for CPS in industrial IoT environments to address these challenges. Unlike traditional IDS models, Cyber-Sentinet integrates Shapley Additive Explanations (SHAP) to enhance the interpretability of its decision-making process, allowing security experts to understand better and trust the system's detections. Rigorous experimentation on the Edge-IIoT-2022 dataset, which covers various cyber-attacks (e.g., DDoS, SQL injection, MITM), validates Cyber-Sentinet effectiveness. The model achieves an accuracy of 97.46 %, precision of 97.7 %, and recall of 97.2 %, with a low loss of 0.182. These results demonstrate Cyber-Sentinet ability to offer high-performance intrusion detection and valuable insights into network security, making it a robust solution for protecting Industry 5.0 CPS against sophisticated cyber threats.
{"title":"Securing Industry 5.0: An explainable deep learning model for intrusion detection in cyber-physical systems","authors":"Himanshu Nandanwar, Rahul Katarya","doi":"10.1016/j.compeleceng.2025.110161","DOIUrl":"10.1016/j.compeleceng.2025.110161","url":null,"abstract":"<div><div>Cyber-physical systems (CPS) security is critical, particularly with the advent of Industry 5.0, which seeks to revolutionize industrial ecosystems through enhanced automation, connectivity, and human-machine collaboration. While this shift promises increased efficiency and productivity, it exposes systems to advanced cyber threats. This paper introduces Cyber-Sentinet, a Deep Learning-based Intrusion Detection System (IDS) designed explicitly for CPS in industrial IoT environments to address these challenges. Unlike traditional IDS models, Cyber-Sentinet integrates Shapley Additive Explanations (SHAP) to enhance the interpretability of its decision-making process, allowing security experts to understand better and trust the system's detections. Rigorous experimentation on the Edge-IIoT-2022 dataset, which covers various cyber-attacks (e.g., DDoS, SQL injection, MITM), validates Cyber-Sentinet effectiveness. The model achieves an accuracy of 97.46 %, precision of 97.7 %, and recall of 97.2 %, with a low loss of 0.182. These results demonstrate Cyber-Sentinet ability to offer high-performance intrusion detection and valuable insights into network security, making it a robust solution for protecting Industry 5.0 CPS against sophisticated cyber threats.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110161"},"PeriodicalIF":4.0,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-21DOI: 10.1016/j.compeleceng.2025.110185
Boutheina Jlifi , Syrine Ferjani , Claude Duvallet
To overcome Climate Change, countries are turning to greener transportation systems. Therefore, the use of Electric Vehicles (EVs) is leveraging substantially since they present multiple advantages, like reducing hazardous emissions. Recently, the demand for EVs has increased, which means that more charging stations need to be available. By the year 2030, 15 million EVs will be accessible, and since the number of charging stations is limited, the charging needs should be defined for better management of the charging infrastructure. In this research, we aim to tackle this problem by efficiently predicting the energy consumption of EVs. We proposed a Genetic Algorithm (GA) based Three HyperParameter optimization of Deep Long Short Term Memory (GA3P-DLSTM), which is an optimized LSTM model that incorporates a GA for Hyperparameter Tuning. After experimenting our methodology and performing a comparative analysis with previous studies from the literature, the obtained results showed the efficiency of our novel model, with Mean Squared Error (MSE) equals to 0.000112 and a Determination Coefficient (R) equals to 0.96470. It outperformed other models of the literature for predicting energy use based on real-world data collected from the campus of Georgia Tech in Atlanta, USA.
{"title":"A Genetic Algorithm based Three HyperParameter optimization of Deep Long Short Term Memory (GA3P-DLSTM) for Predicting Electric Vehicles energy consumption","authors":"Boutheina Jlifi , Syrine Ferjani , Claude Duvallet","doi":"10.1016/j.compeleceng.2025.110185","DOIUrl":"10.1016/j.compeleceng.2025.110185","url":null,"abstract":"<div><div>To overcome Climate Change, countries are turning to greener transportation systems. Therefore, the use of Electric Vehicles (EVs) is leveraging substantially since they present multiple advantages, like reducing hazardous emissions. Recently, the demand for EVs has increased, which means that more charging stations need to be available. By the year 2030, 15 million EVs will be accessible, and since the number of charging stations is limited, the charging needs should be defined for better management of the charging infrastructure. In this research, we aim to tackle this problem by efficiently predicting the energy consumption of EVs. We proposed a Genetic Algorithm (GA) based Three HyperParameter optimization of Deep Long Short Term Memory (GA3P-DLSTM), which is an optimized LSTM model that incorporates a GA for Hyperparameter Tuning. After experimenting our methodology and performing a comparative analysis with previous studies from the literature, the obtained results showed the efficiency of our novel model, with Mean Squared Error (MSE) equals to 0.000112 and a Determination Coefficient (R<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span>) equals to 0.96470. It outperformed other models of the literature for predicting energy use based on real-world data collected from the campus of Georgia Tech in Atlanta, USA.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110185"},"PeriodicalIF":4.0,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464336","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号